© 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. 634
    Prev
    Next
    INDEX
    Explanations

    HTML formatting components

    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
    1871
    +0.09
    0.2%
    30
    +0.08
    0.2%
    1909
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.09
    0.01
    1120
    +0.08
    0.03
    1343
    +0.08
    0.03
    Negative Logits
     encomp
    -1.80
     Juf
    -1.77
     apprehen
    -1.76
     quitted
    -1.76
     increa
    -1.72
     reluct
    -1.69
     emphat
    -1.69
     intersper
    -1.67
     vainly
    -1.62
     guarante
    -1.57
    POSITIVE LOGITS
     </
    1.43
    ;</
    1.41
    </
    1.41
    }</
    1.40
    )</
    1.38
    ----</
    1.35
    ></
    1.35
    ...</
    1.33
    "></
    1.31
    .</
    1.28
    Activations Density 0.206%

    No Known Activations