© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions and societal issues such as discrimination and labor relations

    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
    604
    +0.16
    0.5%
    764
    +0.09
    0.3%
    1553
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.16
    0.05
    963
    +0.09
    0.04
    182
    +0.08
    0.05
    Negative Logits
    <bos>
    -0.98
     vété
    -0.69
    !!</
    -0.69
     luigi
    -0.67
     chevalier
    -0.66
     TokenType
    -0.65
     pcx
    -0.64
    tagHelperRunner
    -0.64
     frambo
    -0.62
     [''
    -0.62
    POSITIVE LOGITS
     contributes
    0.49
     contribute
    0.49
     hampers
    0.49
     resulting
    0.48
     inefficient
    0.46
    Kaip
    0.45
     foster
    0.45
     result
    0.44
     creates
    0.44
     fuels
    0.44
    Activations Density 0.535%

    No Known Activations