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. 1188
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential hazards or safety precautions

    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
    946
    +0.13
    0.4%
    738
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.05
    1119
    +0.11
    0.03
    965
    +0.10
    0.04
    Negative Logits
     unden
    -0.86
     benevol
    -0.84
     accla
    -0.82
     unve
    -0.82
     parlar
    -0.81
     poichè
    -0.80
     Juf
    -0.80
     embra
    -0.80
     reluct
    -0.80
     revan
    -0.79
    POSITIVE LOGITS
     whenever
    0.60
     unless
    0.55
     wherever
    0.53
     vsak
    0.49
     Startseite
    0.49
     anytime
    0.49
     Whenever
    0.48
     veliko
    0.48
    ırken
    0.48
     orice
    0.47
    Activations Density 0.310%

    No Known Activations