© 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. 31-GEMMASCOPE-RES-16K
    6. 2598
    Prev
    Next
    INDEX
    Explanations

    instances of loyalty and allegiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words preceded by "and" in conjunctive structures that connect related clauses or ideas.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.54
     acestea
    -0.45
    yarnpkg
    -0.43
     AssemblyCompany
    -0.41
     zapato
    -0.39
    兩人
    -0.39
    两人
    -0.38
     orgánico
    -0.38
    aternion
    -0.36
     mecánico
    -0.36
    POSITIVE LOGITS
     its
    0.84
     ourselves
    0.71
     itself
    0.66
     herself
    0.65
     himself
    0.64
     yourself
    0.63
     themselves
    0.59
     our
    0.58
     yourselves
    0.57
     Himself
    0.55
    Activations Density 0.440%

    No Known Activations