© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2542
    Prev
    Next
    INDEX
    Explanations

    community guidelines and instructions for engaging in a community forum

    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
    332
    +0.09
    0.3%
    455
    +0.09
    0.3%
    1882
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1882
    +0.09
    0.06
    1380
    +0.09
    0.01
    1553
    +0.09
    0.06
    Negative Logits
     reluct
    -1.55
     impractica
    -1.46
     inev
    -1.46
     increa
    -1.44
     excru
    -1.43
     fta
    -1.42
     squa
    -1.41
     volunte
    -1.40
     unve
    -1.39
     indestru
    -1.39
    POSITIVE LOGITS
     respect
    0.95
     respectful
    0.92
    respect
    0.82
     courteous
    0.73
     respects
    0.73
     avoid
    0.72
     Respect
    0.72
     conduct
    0.66
    Respect
    0.65
     respecting
    0.65
    Activations Density 0.668%

    No Known Activations