© 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. 433
    Prev
    Next
    INDEX
    Explanations

    locations/facilities that are mentioned in the texts

    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
    805
    +0.08
    0.2%
    966
    +0.07
    0.2%
    1754
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.01
    1363
    +0.07
    0.04
    184
    +0.07
    0.02
    Negative Logits
    TestTools
    -0.57
    Kamera
    -0.56
    Abril
    -0.56
    phorbia
    -0.55
    ValueStyle
    -0.55
    belec
    -0.55
    openqa
    -0.54
    CodeAttribute
    -0.54
    skyl
    -0.53
    ExtendWith
    -0.53
    POSITIVE LOGITS
     Alto
    1.43
    calypse
    1.29
    Alto
    1.08
     ALTO
    1.03
     alto
    0.94
    seigneur
    0.89
    calyptic
    0.87
     lourdes
    0.84
    alto
    0.79
    calyp
    0.78
    Activations Density 0.398%

    No Known Activations