© 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. 2305
    Prev
    Next
    INDEX
    Explanations

    terms related to interdisciplinary studies and research

    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
    1870
    +0.14
    0.4%
    161
    +0.09
    0.3%
    605
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.14
    0.01
    1363
    +0.09
    0.03
    1884
    +0.08
    0.02
    Negative Logits
     reger
    -1.17
     realis
    -0.93
     turbul
    -0.93
     dras
    -0.90
     spont
    -0.89
     obligator
    -0.89
     pessi
    -0.89
     flot
    -0.88
     anse
    -0.86
     neve
    -0.84
    POSITIVE LOGITS
    disciplinary
    2.01
    disciplinar
    1.27
     paradiso
    1.12
     paesaggio
    0.94
     Pièces
    0.93
     medesimo
    0.89
     carrefour
    0.89
     conç
    0.85
     Dijo
    0.85
    rehensive
    0.84
    Activations Density 0.234%

    No Known Activations