© 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. 14229
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative actions or bills

    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%
    2006
    +0.11
    0.3%
    1013
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2006
    +0.13
    0.07
    1734
    +0.11
    0.05
    1705
    +0.09
    0.06
    Negative Logits
     meis
    -1.38
     franz
    -1.34
     cannes
    -1.25
     doman
    -1.21
     loup
    -1.16
     jacques
    -1.15
     hej
    -1.14
     lele
    -1.13
     utop
    -1.13
     chande
    -1.12
    POSITIVE LOGITS
    <bos>
    0.83
     containing
    0.78
     involving
    0.77
     relating
    0.74
     aimed
    0.72
     that
    0.71
     called
    0.70
     regarding
    0.68
     designed
    0.68
     which
    0.67
    Activations Density 0.471%

    No Known Activations