© 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. 580
    Prev
    Next
    INDEX
    Explanations

    the word "straw" in various contexts

    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
    61
    +0.07
    0.2%
    1548
    +0.07
    0.2%
    1910
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.07
    0.02
    1363
    +0.07
    0.02
    783
    +0.07
    0.03
    Negative Logits
    <>
    -0.71
     comme
    -0.70
     aus
    -0.63
    jan
    -0.61
    protected
    -0.61
    Collections
    -0.61
     som
    -0.60
     sie
    -0.60
    \{\\
    -0.59
    予
    -0.59
    POSITIVE LOGITS
     stockholm
    2.07
     chrysler
    1.98
     affor
    1.95
     lidl
    1.94
     michelin
    1.92
     snoopy
    1.90
     toledo
    1.89
     ibiza
    1.87
     tucson
    1.85
     eiffel
    1.84
    Activations Density 0.273%

    No Known Activations