© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97404
    Prev
    Next
    INDEX
    Explanations

    the word "slices" and its variations in various contexts

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

    slice of

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AutoScaleMode
    -0.40
    ༘
    -0.38
     setEmail
    -0.36
    SPATH
    -0.36
    RequiresApi
    -0.36
     /#
    -0.33
    glTexCoord
    -0.33
    Gros
    -0.33
    mailto
    -0.33
     Gros
    -0.32
    POSITIVE LOGITS
    Slice
    2.31
     Slice
    1.82
     createSlice
    1.64
     slice
    1.40
    Slices
    1.33
    slices
    1.28
    slice
    1.15
     slices
    1.13
     slicing
    1.12
     sliced
    0.91
    Activations Density 0.002%

    No Known Activations