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. 15273
    Prev
    Next
    INDEX
    Explanations

    references to compositions, properties, and applications of wood and forestry-related materials

    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
    ValueStyle
    -0.63
    ագրություններ
    -0.62
    ThroughAttribute
    -0.60
    ########.
    -0.54
     Kef
    -0.52
    ApiModelProperty
    -0.51
     Scripts
    -0.48
    setVerticalGroup
    -0.48
    PendingIntent
    -0.48
    GeneratedCode
    -0.47
    POSITIVE LOGITS
     timber
    0.94
     wood
    0.91
    timber
    0.86
     kayu
    0.80
    Timber
    0.79
     Timber
    0.79
     forest
    0.78
     lumber
    0.76
    木材
    0.76
     چوب
    0.76
    Activations Density 0.221%

    No Known Activations