© 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. 790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1120
    +0.12
    0.3%
    1013
    +0.09
    0.3%
    81
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.10
    283
    +0.09
    0.03
    690
    +0.08
    0.07
    Negative Logits
    <bos>
    -1.00
    Cerrar
    -0.81
    kháu
    -0.79
    Continuar
    -0.77
    ѝ
    -0.76
    rungsseite
    -0.75
    Salir
    -0.74
     ter
    -0.74
     getItemId
    -0.73
    ArgsConstructor
    -0.73
    POSITIVE LOGITS
     milf
    2.23
     lamborghini
    2.23
     outlander
    2.19
     ftu
    2.13
     pegasus
    2.13
     madonna
    2.13
     perfet
    2.12
     bordeaux
    2.11
     maneu
    2.09
     desir
    2.08
    Activations Density 0.279%

    No Known Activations