© 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. 622
    Prev
    Next
    INDEX
    Explanations

    words related to technology, specifically hardware specifications

    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
    370
    +0.08
    0.2%
    1604
    +0.08
    0.2%
    1677
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.04
    1363
    +0.08
    0.03
    283
    +0.08
    0.01
    Negative Logits
    cshtml
    -0.82
     mit
    -0.74
    complexType
    -0.72
    case
    -0.71
     <<<<<<<<<<<<<<
    -0.70
     intptr
    -0.69
    ParallelGroup
    -0.69
     stop
    -0.68
    WithIdentifier
    -0.67
     кв
    -0.67
    POSITIVE LOGITS
    ek
    2.41
     stockholm
    2.07
     increa
    2.04
     strick
    1.99
     maneu
    1.98
     sergio
    1.98
     jorge
    1.95
     ricardo
    1.95
     guarante
    1.93
     perfet
    1.92
    Activations Density 0.258%

    No Known Activations