Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 160
    Prev
    Next
    INDEX
    Explanations

    mentions of people being named for recognition or awards

    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
    50
    +0.11
    0.4%
    1895
    +0.06
    0.2%
    2011
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.11
    0.03
    1895
    +0.06
    0.03
    968
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.46
    ൊ
    -0.90
    /**
    -0.88
    //
    -0.87
    public
    -0.87
    ണ്ട
    -0.87
    invokeLater
    -0.86
    ///
    -0.85
    </table>
    -0.83
    /**
    
    -0.82
    POSITIVE LOGITS
     maneu
    3.15
     affor
    3.02
     increa
    2.94
     accla
    2.92
     shenan
    2.90
     impra
    2.87
     reluct
    2.86
     disagre
    2.84
     emphat
    2.72
     inev
    2.71
    Activations Density 0.108%

    No Known Activations