© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 265
    Prev
    Next
    INDEX
    Explanations

    references to specific newspapers

    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
    1961
    +0.11
    0.3%
    1604
    +0.09
    0.3%
    31
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.11
    0.02
    1363
    +0.09
    0.02
    1075
    +0.08
    0.02
    Negative Logits
     pinch
    -0.91
     simpel
    -0.70
     Pinch
    -0.67
    Tikang
    -0.67
    DoubleQuotes
    -0.66
     kram
    -0.65
    <bos>
    -0.63
    Pinch
    -0.61
     sement
    -0.61
    KELEY
    -0.61
    POSITIVE LOGITS
     Herald
    2.79
    Herald
    2.40
    herald
    1.93
     herald
    1.69
    ERALD
    0.96
     heral
    0.92
     considér
    0.86
     montrant
    0.83
    bumper
    0.83
     clô
    0.75
    Activations Density 0.188%

    No Known Activations