© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    information related to surnames, particularly those of Polish and Jewish origin

    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
    1967
    +0.29
    1.2%
    1343
    +0.27
    1.1%
    964
    +0.23
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.29
    0.04
    1343
    +0.27
    0.08
    198
    +0.23
    0.07
    Negative Logits
     reconno
    -0.71
     resear
    -0.70
     maneu
    -0.68
     unve
    -0.66
     indestru
    -0.65
     michelin
    -0.64
     Febru
    -0.61
     vry
    -0.60
     volunte
    -0.60
     pessi
    -0.60
    POSITIVE LOGITS
    AutoresizingMask
    0.55
    ConstraintMaker
    0.53
     noong
    0.46
     habang
    0.46
    RectangleBorder
    0.46
    LayoutConstraint
    0.42
    SequentialGroup
    0.42
    straint
    0.42
     BoxFit
    0.41
    malink
    0.41
    Activations Density 0.913%

    No Known Activations