© 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. 13741
    Prev
    Next
    INDEX
    Explanations

    instructions or steps to complete a specific task, such as navigating through menus or creating themes

    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
    251
    +0.18
    0.6%
    674
    +0.11
    0.4%
    1053
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.18
    0.11
    166
    +0.11
    0.06
    1053
    +0.10
    0.06
    Negative Logits
    乓
    -0.45
    FontFamily
    -0.43
    łaszcza
    -0.43
     Nhi
    -0.42
    aquin
    -0.40
     Dla
    -0.40
    Responsibility
    -0.40
    newsletter
    -0.39
    ítez
    -0.38
     regno
    -0.38
    POSITIVE LOGITS
     goin
    0.88
     go
    0.86
     goTo
    0.85
    Goes
    0.83
     went
    0.81
     GOING
    0.81
    went
    0.80
     going
    0.80
     Went
    0.77
    goes
    0.76
    Activations Density 0.162%

    No Known Activations