© 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. 420
    Prev
    Next
    INDEX
    Explanations

    phrases related to product specifications and features

    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
    1622
    +0.07
    0.2%
    1316
    +0.07
    0.2%
    523
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.04
    1363
    +0.07
    0.07
    1343
    +0.07
    0.09
    Negative Logits
     Krzysz
    -0.75
     Warszaw
    -0.67
     Infatti
    -0.65
     Sprecher
    -0.64
     Fürst
    -0.64
     dichi
    -0.61
    ęło
    -0.60
    unft
    -0.59
    openha
    -0.59
    culadora
    -0.59
    POSITIVE LOGITS
    acky
    1.06
     levis
    0.77
    vastatin
    0.76
     Apri
    0.75
     maer
    0.73
     eorum
    0.72
     Toi
    0.69
     gracilis
    0.69
     sibi
    0.68
     glau
    0.67
    Activations Density 0.602%

    No Known Activations