© 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. 0-GEMMASCOPE-RES-16K
    6. 7979
    Prev
    Next
    INDEX
    Explanations

    references to rural areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.88
     desmotivaciones
    -0.84
     resourceCulture
    -0.83
    pecabe
    -0.82
     autorytatywna
    -0.81
    ]")]
    -0.79
    WebVitals
    -0.79
     wireType
    -0.77
    +#+#
    -0.77
     ProtoMessage
    -0.76
    POSITIVE LOGITS
    include
    0.69
    ↵↵
    0.63
    Nullable
    0.58
    com
    0.58
    android
    0.57
    unset
    0.55
    <strong>
    0.54
    org
    0.54
    in
    0.54
    2
    0.54
    Activations Density 0.301%

    No Known Activations