Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14967
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion, especially those related to gossip and negative remarks about others

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

    Statements, remarks, or talking about someone

    np_acts-logits-general · gemini-2.0-flash

    speeches, remarks, talking, singing, criticism, praise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.53
    enumii
    -0.53
     Negotiation
    -0.52
    COUVER
    -0.52
    stdc
    -0.50
    Negoti
    -0.50
    ρας
    -0.46
    GRI
    -0.46
    IsContent
    -0.46
     vân
    -0.45
    POSITIVE LOGITS
     praise
    1.28
     praising
    1.28
     criticism
    1.20
     dispar
    1.19
     derogatory
    1.19
     criticisms
    1.16
     praises
    1.15
     slander
    1.12
     criticizing
    1.10
     negative
    1.08
    Activations Density 0.357%

    No Known Activations