© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11474
    Prev
    Next
    INDEX
    Explanations

    references to a specific recurring element or concept for analysis or comparison

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    662
    +0.14
    0.5%
    812
    +0.14
    0.5%
    1052
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.14
    0.02
    1425
    +0.14
    0.02
    812
    +0.13
    0.02
    Negative Logits
     renou
    -0.48
    RTHOOK
    -0.47
    Viitteet
    -0.46
     convaincre
    -0.45
    Primes
    -0.45
     Selby
    -0.44
     Stuffed
    -0.44
    Décès
    -0.43
     Suc
    -0.43
     Rigby
    -0.42
    POSITIVE LOGITS
     pattern
    1.44
    pattern
    1.37
     patterns
    1.34
     Pattern
    1.29
    Pattern
    1.27
     Patterns
    1.15
     PATTERN
    1.14
    patterns
    1.11
    Patterns
    1.10
    PATTERN
    1.09
    Activations Density 0.052%

    No Known Activations