© 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. 33-GEMMASCOPE-RES-16K
    11. 46
    Prev
    Next
    INDEX
    Explanations

    phrases related to estimations and assessments of value or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.48
     when
    -0.40
     когда
    -0.37
    +:+
    -0.36
    LikeLike
    -0.35
    RegressionTest
    -0.35
     and
    -0.34
    我了
    -0.34
    EZ
    -0.34
     
    -0.33
    POSITIVE LOGITS
     them
    0.65
     totul
    0.57
    rungsseite
    0.55
     it
    0.53
     Chwiliwch
    0.53
     Numerade
    0.50
    principalColumn
    0.50
    rawDesc
    0.50
    把
    0.50
    WriteAttribute
    0.49
    Activations Density 0.812%

    No Known Activations