© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1007
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "if not" used 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
    674
    +0.18
    0.6%
    1265
    +0.10
    0.3%
    404
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.18
    0.05
    757
    +0.10
    0.05
    1265
    +0.10
    0.04
    Negative Logits
     pymysql
    -0.93
     smtplib
    -0.84
     psycopg
    -0.80
     actionTypes
    -0.76
     hcm
    -0.74
    graphicx
    -0.67
     pylab
    -0.66
     miu
    -0.63
     pymongo
    -0.63
     heapq
    -0.62
    POSITIVE LOGITS
     if
    0.75
    if
    0.71
     Mère
    0.61
     IF
    0.59
     iesp
    0.59
    If
    0.54
     monsieur
    0.53
    posób
    0.53
     nếu
    0.53
     jika
    0.53
    Activations Density 0.136%

    No Known Activations