© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2646
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or terms (e.g., "Ariel" or "snapshot") in the text

    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
    341
    +0.13
    0.4%
    313
    +0.11
    0.3%
    32
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.13
    0.05
    1120
    +0.11
    0.05
    1363
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.81
    migrationBuilder
    -0.67
    RefNanny
    -0.61
    LOYEES
    -0.59
    incón
    -0.54
     امريكا
    -0.53
    TagHelper
    -0.53
     متحده
    -0.53
    getNome
    -0.52
    finance
    -0.52
    POSITIVE LOGITS
     ariel
    1.86
     Ariel
    1.47
    Ariel
    1.23
     lidl
    1.18
     volunte
    1.12
     rancho
    1.09
     toledo
    1.08
     seoul
    1.06
     inol
    1.05
    ariel
    1.05
    Activations Density 0.347%

    No Known Activations