© 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. 14222
    Prev
    Next
    INDEX
    Explanations

    mentions of safety and specific locations

    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
    466
    +0.08
    0.2%
    833
    +0.07
    0.2%
    510
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.08
    0.04
    466
    +0.07
    0.04
    1261
    +0.06
    0.01
    Negative Logits
     maneu
    -1.48
     increa
    -1.42
     inev
    -1.40
     impra
    -1.37
     squa
    -1.36
     erad
    -1.35
     fuf
    -1.34
     excru
    -1.33
     reluct
    -1.33
     disagre
    -1.33
    POSITIVE LOGITS
     others
    0.88
     Others
    0.76
    Others
    0.64
    IsMutable
    0.63
    others
    0.63
     teammates
    0.58
     lagar
    0.57
     OTHERS
    0.57
    آخر
    0.56
     близь
    0.56
    Activations Density 0.274%

    No Known Activations