© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9482
    Prev
    Next
    INDEX
    Explanations

    error handling and information retrieval related to APIs or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.78
     CURIAM
    -0.66
    HostException
    -0.63
    UrlResolution
    -0.63
     وتسجيلات
    -0.61
    Autoritní
    -0.59
     Normdatei
    -0.59
     Италијани
    -0.58
    AndEndTag
    -0.56
     varargin
    -0.54
    POSITIVE LOGITS
     InputDecoration
    0.53
     containing
    0.44
    NSIndexPath
    0.40
     attached
    0.39
    containing
    0.39
     information
    0.37
     pack
    0.37
     specs
    0.36
     replete
    0.34
    pack
    0.34
    Activations Density 0.631%

    No Known Activations