© 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. 7648
    Prev
    Next
    INDEX
    Explanations

    information related to explosive devices and terrorist attacks

    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
    +0.12
    0.4%
    394
    +0.12
    0.4%
    1018
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1018
    +0.12
    0.05
    946
    +0.12
    0.04
    394
    +0.11
    0.04
    Negative Logits
     wien
    -0.96
     wein
    -0.95
     marte
    -0.92
     ananas
    -0.92
     inder
    -0.91
     doman
    -0.90
     blin
    -0.90
     franz
    -0.90
     glan
    -0.89
     ché
    -0.87
    POSITIVE LOGITS
     deton
    0.66
     bomb
    0.64
     explosives
    0.62
     bombs
    0.57
    Πηγές
    0.57
     hornblende
    0.53
     explosion
    0.52
     explosive
    0.52
    bezpiecz
    0.52
     exploded
    0.50
    Activations Density 0.273%

    No Known Activations