© 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. 13783
    Prev
    Next
    INDEX
    Explanations

    terms related to specific concepts and entities, like flavors, behaviors, materials, and 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
    1783
    +0.11
    0.3%
    394
    +0.09
    0.2%
    1539
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1783
    +0.11
    0.05
    1748
    +0.09
    0.03
    1539
    +0.09
    0.03
    Negative Logits
     ***!
    -0.72
    ControllerAdvice
    -0.50
     مرئيه
    -0.49
    ğına
    -0.49
    Elő
    -0.47
     officiels
    -0.47
    getreten
    -0.45
    CascadeType
    -0.45
     conséquence
    -0.45
    LabelTagHelper
    -0.45
    POSITIVE LOGITS
     ftu
    1.06
     ftre
    0.97
     paff
    0.95
     effe
    0.91
     waer
    0.90
     thut
    0.89
     „,
    0.89
     canel
    0.88
     myn
    0.88
     dises
    0.88
    Activations Density 0.244%

    No Known Activations