© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 886
    Prev
    Next
    INDEX
    Explanations

    information related to blood donation and medical history, specifically regarding a person named Harrison and the discovery of the Rhesus factor and mitochondrial DNA

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    872
    +0.14
    0.4%
    283
    +0.12
    0.3%
    1150
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.14
    0.06
    295
    +0.12
    0.01
    203
    +0.11
    0.04
    Negative Logits
     autorytatywna
    -0.68
    RegressionTest
    -0.65
     nakalista
    -0.62
     Wiking
    -0.61
    CppMethod
    -0.61
    RuleContext
    -0.61
    UDAD
    -0.60
    Autoritní
    -0.60
     betweenstory
    -0.60
    millimeters
    -0.59
    POSITIVE LOGITS
     unwarran
    1.31
     disagre
    1.23
     cytoplas
    1.16
     pymysql
    1.16
     increa
    1.09
     apprehen
    1.07
     impractica
    1.06
     zipfile
    1.06
     uninten
    1.06
     indestru
    1.05
    Activations Density 0.593%

    No Known Activations