© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    scientific and technical details, including measurements, regulations, and monitoring procedures

    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
    1978
    +0.15
    0.5%
    478
    +0.11
    0.3%
    636
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1304
    +0.15
    0.05
    1499
    +0.11
    0.06
    577
    +0.10
    0.04
    Negative Logits
    Tē
    -0.80
     مرئيه
    -0.77
     ujednoznacz
    -0.74
    tonode
    -0.73
    LayoutStyle
    -0.72
    Datuak
    -0.70
    fromnode
    -0.70
    intios
    -0.69
    الحياه
    -0.69
    uxxxx
    -0.69
    POSITIVE LOGITS
     disagre
    1.40
     ineffec
    1.32
     apprehen
    1.30
     depic
    1.29
     shenan
    1.28
     indescri
    1.25
     inconce
    1.23
     impra
    1.22
     maneu
    1.19
     tolerably
    1.19
    Activations Density 0.222%

    No Known Activations