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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6848
    Prev
    Next
    INDEX
    Explanations

    text related to customer service and return policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     general
    -0.51
    ganu
    -0.47
    ]--;
    -0.47
     الرياضيه
    -0.47
    SequentialGroup
    -0.46
    snap
    -0.45
     self
    -0.45
    ')));
    -0.45
    "]));
    -0.45
     endforeach
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    0.67
     createSlice
    0.66
    PreferredItem
    0.65
    पया
    0.61
    CodedInputStream
    0.59
    getDescriptor
    0.59
     sostitu
    0.58
     désolés
    0.58
    createCell
    0.57
     recev
    0.55
    Activations Density 0.200%

    No Known Activations