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. 7-GEMMASCOPE-RES-16K
    6. 9581
    Prev
    Next
    INDEX
    Explanations

    actions related to confrontation and defense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mapStateToProps
    -0.42
     前
    -0.42
    息
    -0.40
    getDocument
    -0.39
     objetivos
    -0.39
     Wednesday
    -0.38
    -
    -0.38
    暗
    -0.37
     tắt
    -0.37
     l
    -0.37
    POSITIVE LOGITS
     repel
    1.02
     repelled
    0.93
     repellent
    0.81
     eviction
    0.81
     deterrent
    0.81
     expulsion
    0.80
    deter
    0.74
    ربای
    0.73
    fitriones
    0.73
     dispel
    0.73
    Activations Density 0.278%

    No Known Activations