© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    actions or events related to military operations or conflicts

    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
    1553
    +0.09
    0.3%
    1533
    +0.07
    0.2%
    1013
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1827
    +0.09
    0.04
    1288
    +0.07
    0.05
    1030
    +0.07
    0.03
    Negative Logits
     increa
    -1.23
     guarante
    -1.20
     resear
    -1.12
     inev
    -1.11
     secon
    -1.10
     desir
    -1.09
     affor
    -1.07
     alre
    -1.06
     volunte
    -1.06
     santiago
    -1.03
    POSITIVE LOGITS
    VYMaps
    0.67
     amid
    0.59
    RectangleBorder
    0.58
     via
    0.57
    Forrás
    0.57
     within
    0.56
     during
    0.56
    Література
    0.55
    Referencoj
    0.55
     without
    0.55
    Activations Density 0.288%

    No Known Activations