© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, specifically Manhattan

    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
    161
    +0.10
    0.4%
    1942
    +0.07
    0.3%
    1950
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.05
    2044
    +0.07
    0.05
    1233
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.80
    FieldBuilder
    -0.78
    <0xF0>
    -0.67
    ത്ത
    -0.66
    ുക
    -0.66
     deliver
    -0.65
     keep
    -0.65
     absorb
    -0.65
    displayquote
    -0.65
    ുറ
    -0.64
    POSITIVE LOGITS
     maneu
    2.15
     affor
    2.12
     stockholm
    2.02
     increa
    2.01
     wien
    1.99
     accla
    1.97
     wikihow
    1.93
     reluct
    1.86
     impra
    1.84
     murano
    1.83
    Activations Density 0.392%

    No Known Activations