© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    phrases related to a military conflict and the aftermath

    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
    184
    +0.14
    0.4%
    946
    +0.12
    0.4%
    511
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.06
    184
    +0.12
    0.03
    509
    +0.11
    0.06
    Negative Logits
    <bos>
    -1.15
     trouva
    -0.84
     cannes
    -0.82
     lende
    -0.78
     applau
    -0.78
     anse
    -0.77
     pantal
    -0.76
     blin
    -0.75
     broder
    -0.75
     tille
    -0.75
    POSITIVE LOGITS
     captured
    0.56
     surrender
    0.54
     spared
    0.52
     surrendered
    0.51
     capture
    0.51
     destruction
    0.49
    machung
    0.49
     massacre
    0.49
     mercy
    0.48
     brutality
    0.47
    Activations Density 0.492%

    No Known Activations