© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2117
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific studio and equipment used in a production setting

    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
    1178
    +0.09
    0.4%
    50
    +0.09
    0.3%
    1140
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    822
    +0.09
    0.04
    450
    +0.09
    0.03
    1178
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.94
    ⓧ
    -0.90
    
    -0.78
    <?
    -0.74
     shivered
    -0.71
     defray
    -0.68
     endow
    -0.68
     shuddered
    -0.67
     overwhel
    -0.64
     leaped
    -0.64
    POSITIVE LOGITS
     studio
    2.36
     Studio
    2.17
    Studio
    2.06
     studios
    2.06
    studio
    2.04
     STUDIO
    1.94
    STUDIO
    1.70
     Studios
    1.68
    Studios
    1.61
    studios
    1.44
    Activations Density 0.155%

    No Known Activations