© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 13444
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or direct speech within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ","
    -0.54
    `,`
    -0.53
    !");
    -0.51
    ','
    -0.51
    aarrggbb
    -0.47
    ]!='
    -0.46
    "+"
    -0.46
    Autoritní
    -0.45
    」、「
    -0.44
    !",
    -0.44
    POSITIVE LOGITS
     Yeah
    1.22
    Yeah
    1.08
    Interviewer
    1.08
     Transcript
    0.96
     interviewer
    0.92
    inaudible
    0.90
     yeah
    0.90
     Okay
    0.86
     Well
    0.82
     INTERVIEW
    0.82
    Activations Density 0.444%

    No Known Activations