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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 652
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data modeling and analysis, particularly emphasizing concepts related to margins and boundaries

    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
    795
    +0.11
    0.3%
    32
    +0.08
    0.2%
    538
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.11
    0.04
    1343
    +0.08
    0.04
    283
    +0.08
    0.01
    Negative Logits
    มา
    -0.69
     кро
    -0.69
    正
    -0.69
     finish
    -0.67
     signed
    -0.67
    WriteAttribute
    -0.67
     опо
    -0.66
    SPATH
    -0.66
    أ
    -0.66
    ب
    -0.66
    POSITIVE LOGITS
     emphat
    2.65
     desir
    2.49
     increa
    2.42
     milf
    2.38
     guarante
    2.35
     depic
    2.32
     maneu
    2.31
     fuf
    2.31
     accla
    2.31
     affor
    2.27
    Activations Density 0.350%

    No Known Activations