© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4618
    Prev
    Next
    INDEX
    Explanations

    the concept of "reaching" or attaining a goal or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.38
     defaultstate
    -0.38
     autorytatywna
    -0.36
    المصادر
    -0.33
    ecma
    -0.33
     keeping
    -0.32
    достатки
    -0.32
    ก่
    -0.32
     laund
    -0.30
     hiding
    -0.30
    POSITIVE LOGITS
     reaching
    2.31
     Reaching
    2.17
    Reaching
    2.14
    reaching
    2.05
     hitting
    1.47
     reaches
    1.30
    hitting
    1.27
     REACH
    1.10
     mencapai
    1.09
     approaching
    1.07
    Activations Density 0.298%

    No Known Activations