© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13862
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainties

    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
    1735
    +0.07
    0.2%
    917
    +0.07
    0.2%
    1510
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.07
    0.04
    907
    +0.07
    0.03
    1735
    +0.07
    0.03
    Negative Logits
     emphat
    -1.21
     increa
    -1.21
     intermitt
    -1.09
     impra
    -1.04
     alre
    -1.04
     depic
    -1.04
     maneu
    -1.03
     reluct
    -1.03
     strick
    -1.03
     uninten
    -1.02
    POSITIVE LOGITS
    OGND
    0.76
     how
    0.69
    how
    0.69
    AnchorStyles
    0.67
    wavering
    0.65
    verifyException
    0.63
    MLLoader
    0.63
    @[+][
    0.62
    thinkable
    0.61
    Espèce
    0.61
    Activations Density 0.286%

    No Known Activations