© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7784
    Prev
    Next
    INDEX
    Explanations

    terms related to technology updates and historical events, particularly disease outbreaks and scientific descriptions

    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
    1870
    +0.13
    0.4%
    1042
    +0.10
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    324
    +0.13
    0.03
    1789
    +0.10
    0.04
    678
    +0.10
    0.04
    Negative Logits
     للاسماء
    -0.61
     BIBSYS
    -0.59
    脚注の使い方
    -0.59
    fromnode
    -0.58
    epik
    -0.54
     koc
    -0.54
     Ouverture
    -0.54
     Majesté
    -0.53
     سكانية
    -0.53
    AccessorTable
    -0.53
    POSITIVE LOGITS
    Rgds
    0.88
     maneu
    0.85
     jorge
    0.83
    “…”
    0.81
     shenan
    0.81
     reluct
    0.78
     sergio
    0.76
     attemp
    0.76
     ricardo
    0.76
     emphat
    0.76
    Activations Density 0.402%

    No Known Activations