© 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. 558
    Prev
    Next
    INDEX
    Explanations

    addresses, locations, and event details

    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
    544
    +0.09
    0.3%
    992
    +0.07
    0.2%
    1806
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.09
    0.03
    992
    +0.07
    0.03
    1013
    +0.07
    0.03
    Negative Logits
    
    -0.69
    <?
    -0.63
    //
    -0.58
     respond
    -0.56
    #
    -0.55
    자
    -0.53
    ⓧ
    -0.53
    displayquote
    -0.53
    HasIndex
    -0.53
     raise
    -0.52
    POSITIVE LOGITS
     Blvd
    3.03
     Boulevard
    2.90
     boulevard
    1.97
     BOU
    1.17
    levard
    1.14
     swarovski
    1.14
     embodi
    1.12
     territo
    1.11
     maer
    1.09
     glau
    1.07
    Activations Density 0.211%

    No Known Activations