© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4779
    Prev
    Next
    INDEX
    Explanations

    references to specific organizations or groups, particularly with the initials "UM" or "CM."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.68
    wantErr
    -0.52
    ngdoc
    -0.49
    fjspx
    -0.47
    principalColumn
    -0.46
    amilya
    -0.46
     ComVisible
    -0.45
    balleur
    -0.44
    istungs
    -0.43
     Philadel
    -0.43
    POSITIVE LOGITS
    ंदीखरीदारी
    0.43
    -------
    0.41
    CM
    0.39
     CM
    0.38
    Lähteet
    0.37
    İstinadlar
    0.37
    日閲覧
    0.37
    cm
    0.36
    Sucesor
    0.36
    InteropServices
    0.34
    Activations Density 0.317%

    No Known Activations