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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 247
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and technical document content

    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
    752
    +0.10
    0.4%
    1120
    +0.10
    0.4%
    823
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.10
    0.17
    1120
    +0.10
    0.16
    823
    +0.06
    0.15
    Negative Logits
     also
    -1.24
     now
    -1.21
     have
    -1.20
     could
    -1.19
     even
    -1.19
     in
    -1.19
     for
    -1.18
    .
    -1.18
     might
    -1.17
     may
    -1.17
    POSITIVE LOGITS
     stockholm
    3.17
     wien
    3.12
     vété
    2.90
     ?...
    2.89
     Juf
    2.85
     mef
    2.84
     véhic
    2.84
     délib
    2.83
     accla
    2.82
     „,
    2.81
    Activations Density 1.626%

    No Known Activations