© 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. 514
    Prev
    Next
    INDEX
    Explanations

    PDF files for download

    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
    24
    +0.08
    0.3%
    50
    +0.07
    0.2%
    67
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1290
    +0.08
    0.03
    1351
    +0.07
    0.03
    370
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.98
     continue
    -0.73
     promote
    -0.67
     deliver
    -0.66
    public
    -0.66
    ,
    -0.66
     to
    -0.65
     offer
    -0.64
     remain
    -0.64
     turn
    -0.64
    POSITIVE LOGITS
     wien
    1.97
     squa
    1.87
     effe
    1.85
     thut
    1.80
     stockholm
    1.78
     fte
    1.76
     volunte
    1.76
     ftu
    1.73
     inev
    1.73
     aen
    1.73
    Activations Density 0.215%

    No Known Activations