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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 279
    Prev
    Next
    INDEX
    Explanations

    descriptions related to ships or vessels

    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
    +0.10
    0.4%
    492
    +0.07
    0.3%
    1937
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.10
    0.04
    2001
    +0.07
    0.04
    1479
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.55
    public
    -0.80
    ുറ
    -0.79
    ,
    -0.77
    .
    -0.76
    echo
    -0.75
    </tbody>
    -0.74
    util
    -0.74
    //
    -0.73
    protected
    -0.72
    POSITIVE LOGITS
     maneu
    2.38
     impra
    2.33
     increa
    2.32
     affor
    2.30
     excru
    2.23
     shenan
    2.16
     accla
    2.15
     stockholm
    2.15
     embodi
    2.14
     emphat
    2.14
    Activations Density 0.102%

    No Known Activations