© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8720
    Prev
    Next
    INDEX
    Explanations

    positive words and phrases that convey improvement or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    variable
    -0.42
     variable
    -0.41
     virtual
    -0.38
     referrerpolicy
    -0.38
    myfile
    -0.38
     dim
    -0.35
    virtual
    -0.34
     foo
    -0.34
    slow
    -0.34
    Variable
    -0.33
    POSITIVE LOGITS
    featureID
    0.66
     ModelExpression
    0.60
     nahilalakip
    0.56
     تكبرها
    0.56
    sidemargin
    0.54
    stdc
    0.52
    JspWriter
    0.49
     esternos
    0.49
    âce
    0.48
    INCREF
    0.47
    Activations Density 0.884%

    No Known Activations