© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    sentences describing social or political conflicts and interactions

    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
    2019
    +0.20
    0.6%
    50
    +0.15
    0.5%
    30
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.20
    0.05
    492
    +0.15
    0.04
    1892
    +0.12
    0.03
    Negative Logits
     quoique
    -1.19
     aussitôt
    -1.05
     volon
    -0.99
     Souha
    -0.98
    !!</
    -0.94
     applau
    -0.94
     quelquefois
    -0.93
     siè
    -0.91
     tantôt
    -0.90
     convenable
    -0.89
    POSITIVE LOGITS
     finally
    0.94
     lastly
    0.92
     ultimately
    0.81
     importantly
    0.77
     even
    0.75
     eventually
    0.69
     occasionally
    0.69
    finally
    0.67
     etc
    0.65
     perhaps
    0.64
    Activations Density 0.183%

    No Known Activations