© 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. 2558
    Prev
    Next
    INDEX
    Explanations

    phrases related to audio file formats and editing

    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
    699
    +0.11
    0.3%
    1971
    +0.09
    0.3%
    871
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.04
    1971
    +0.09
    0.03
    283
    +0.08
    0.01
    Negative Logits
    <bos>
    -0.74
    varnothing
    -0.62
    HasIndex
    -0.60
    typeorm
    -0.60
    esModule
    -0.60
    emptyset
    -0.59
    Хьажоргаш
    -0.56
    กรณ์
    -0.56
     følger
    -0.56
    więcej
    -0.55
    POSITIVE LOGITS
    gg
    2.60
    GG
    1.63
     gg
    1.60
    ggg
    1.46
    gggg
    1.36
     unce
    1.32
     GG
    1.27
     effe
    1.25
     OGS
    1.25
     wherea
    1.21
    Activations Density 0.222%

    No Known Activations