© 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. 9-GEMMASCOPE-RES-16K
    6. 8692
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reach" and its variations, indicating a focus on reaching goals or targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wigs
    -0.49
     flaws
    -0.42
     cows
    -0.42
    enumi
    -0.41
    덟
    -0.41
     kwar
    -0.41
    الدراسه
    -0.40
     wars
    -0.40
     macchine
    -0.40
     thefts
    -0.39
    POSITIVE LOGITS
     reach
    1.98
     Reach
    1.89
     reached
    1.86
    reach
    1.86
    Reach
    1.84
     reaches
    1.76
     reaching
    1.75
    Reaching
    1.72
     Reaching
    1.72
    reached
    1.69
    Activations Density 0.113%

    No Known Activations