Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 81553
    Prev
    Next
    INDEX
    Explanations

    references to failures or poor performances, particularly in a context related to entertainment or products

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

    flop, floppy, flip

    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
    "":
    -0.45
    ngrx
    -0.44
    Lynx
    -0.42
    \"");
    -0.41
    NGL
    -0.41
     UTM
    -0.40
    extAlignment
    -0.40
     "@/
    -0.40
    __":
    -0.40
    UTM
    -0.40
    POSITIVE LOGITS
     flop
    1.90
    flop
    1.69
     flops
    1.65
    Flop
    1.58
    flops
    1.40
     floppy
    1.11
    lop
    0.96
     flip
    0.82
     flapping
    0.82
     Lop
    0.78
    Activations Density 0.004%

    No Known Activations