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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8319
    Prev
    Next
    INDEX
    Explanations

    characteristics and attributes relating to moral alignment and intent, particularly in narratives or role-playing contexts

    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
    PostInfinity
    -0.54
    IsContent
    -0.52
    centiles
    -0.45
     ſind
    -0.44
    pushFollow
    -0.43
     ſeveral
    -0.43
     mármol
    -0.43
    SharedDtor
    -0.42
    MessageTagHelper
    -0.42
     Efq
    -0.42
    POSITIVE LOGITS
     friendly
    0.60
     allied
    0.53
     ally
    0.49
    friendly
    0.48
     hostile
    0.45
     Friendly
    0.44
    plom
    0.42
    inc
    0.42
     sympathetic
    0.41
    友好
    0.40
    Activations Density 0.368%

    No Known Activations