© 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. 21-GEMMASCOPE-RES-16K
    6. 15811
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.49
    /*!
    -0.47
    WriteTagHelper
    -0.46
     כן
    -0.46
    complexType
    -0.43
    apiClient
    -0.43
     VIAF
    -0.42
    }$​
    -0.41
     autom
    -0.41
    fvar
    -0.41
    POSITIVE LOGITS
     merely
    0.79
    แค่
    0.71
    เพียง
    0.66
     mere
    0.65
    只需
    0.60
     лишь
    0.59
     مجرد
    0.58
     cursory
    0.57
    只需要
    0.56
    mere
    0.56
    Activations Density 0.333%

    No Known Activations