© 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. 10-RES-JB
    11. 584
    Prev
    Next
    INDEX
    Explanations

    the presence of specific command-line interface options or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.0%
    876
    +0.13
    0.5%
    453
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.24
    0.01
    453
    +0.13
    0.02
    1516
    +0.12
    0.01
    Negative Logits
    <bos>
    -3.24
    ,
    -0.77
     put
    -0.76
     at
    -0.73
     AssemblyCompany
    -0.72
    和
    -0.71
    .
    -0.71
     in
    -0.70
     for
    -0.70
    }],
    -0.70
    POSITIVE LOGITS
     milano
    2.09
     stockholm
    2.01
     bandung
    1.98
     increa
    1.94
     napoli
    1.93
     lidl
    1.92
     affor
    1.89
     guarante
    1.87
     wikihow
    1.87
     dises
    1.85
    Activations Density 0.028%

    No Known Activations