Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7817
    Prev
    Next
    INDEX
    Explanations

    instances of the word "twice" occurring 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-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
    405
    +0.11
    0.4%
    1013
    +0.10
    0.3%
    1335
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.11
    0.04
    446
    +0.10
    0.03
    1335
    +0.10
    0.03
    Negative Logits
    斯科
    -0.45
    Ethylbenzene
    -0.43
     gynhyrchwyd
    -0.42
    levant
    -0.41
    Dibrom
    -0.41
    ఆ
    -0.39
    QL
    -0.39
     preocupa
    -0.39
    ഒ
    -0.39
    Kapcsolódó
    -0.39
    POSITIVE LOGITS
     Twice
    0.84
     chrysler
    0.84
    twice
    0.78
     unspeak
    0.76
     TWICE
    0.75
    Twice
    0.74
     hilux
    0.74
     thrice
    0.73
     schoolmaster
    0.72
     homeward
    0.72
    Activations Density 0.107%

    No Known Activations