© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13786
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and emotional complexity

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

    Third-person pronouns followed by verbs related to actions

    np_acts-logits-general · gemini-2.0-flash

    action/behavior of subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMID
    -0.51
    ceptual
    -0.51
    agner
    -0.50
     resistance
    -0.49
    arikat
    -0.49
    ivir
    -0.48
    SqlDataReader
    -0.46
     Gefühl
    -0.45
    ίδι
    -0.45
    )++;
    -0.44
    POSITIVE LOGITS
     act
    0.96
     acts
    0.84
     behave
    0.81
    act
    0.80
    Act
    0.78
     ACTS
    0.78
     behaves
    0.77
     Act
    0.76
     acted
    0.76
    acts
    0.73
    Activations Density 0.284%

    No Known Activations