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

    Neuronpedia

    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. 244
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    122
    +0.11
    0.4%
    1323
    +0.10
    0.3%
    200
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.11
    0.03
    1323
    +0.10
    0.03
    501
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.71
     vainly
    -0.65
     strode
    -0.60
     mustered
    -0.58
     engendered
    -0.58
     symbolically
    -0.57
     darted
    -0.56
     leaped
    -0.56
     impelled
    -0.55
     leapt
    -0.54
    POSITIVE LOGITS
     Benjamin
    1.70
    Benjamin
    1.56
     Benjam
    1.16
     catég
    0.96
     Bén
    0.91
    Jenny
    0.88
     Jenny
    0.87
     fasc
    0.84
     polig
    0.83
     Kategor
    0.83
    Activations Density 0.207%

    No Known Activations