© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 604
    Prev
    Next
    INDEX
    Explanations

    references to Pakistan and related geopolitical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    795
    +0.11
    0.4%
    1909
    +0.10
    0.4%
    1778
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.11
    0.03
    683
    +0.10
    0.03
    438
    +0.10
    0.03
    Negative Logits
    <eos>
    -0.71
     may
    -0.68
    ,
    -0.66
     свя
    -0.66
    </table>
    -0.65
     am
    -0.65
     bit
    -0.65
     win
    -0.65
    fillType
    -0.64
    .
    -0.64
    POSITIVE LOGITS
     wien
    2.06
     Abbé
    2.01
     Mlle
    1.96
     coö
    1.89
     madonna
    1.88
     affor
    1.85
     maneu
    1.85
     pakistan
    1.84
     perfet
    1.84
     bordeaux
    1.82
    Activations Density 0.177%

    No Known Activations