© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5966
    Prev
    Next
    INDEX
    Explanations

    terms related to pitching and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    containing "tch" or related sounds

    np_acts-logits-general · gemini-2.0-flash

    pitch, patch, batch, itch endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.53
     möge
    -0.49
    }\|
    -0.47
    り
    -0.46
    oyle
    -0.45
    />";
    -0.45
    `)
    -0.45
    vera
    -0.45
     Teo
    -0.44
     Judea
    -0.44
    POSITIVE LOGITS
    ch
    0.90
    patch
    0.82
     Ach
    0.81
     Patch
    0.81
    Patch
    0.80
     Burch
    0.80
    uch
    0.80
     PATCH
    0.79
    sch
    0.77
    ches
    0.76
    Activations Density 0.675%

    No Known Activations