© 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. 28-GEMMASCOPE-RES-16K
    6. 7567
    Prev
    Next
    INDEX
    Explanations

    phrases related to calculations and evaluations within scientific contexts

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

    Action performed using specific tools or methods

    np_acts-logits-general · gemini-2.0-flash

    actions performed using methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.47
    OGND
    -0.43
    crity
    -0.43
     vixion
    -0.41
    <?
    -0.41
     linkovi
    -0.40
    marvin
    -0.39
     Routine
    -0.39
     plasticity
    -0.38
    deuse
    -0.38
    POSITIVE LOGITS
     using
    1.20
     utilizing
    0.93
     используя
    0.91
     utilizzando
    0.84
     utilizando
    0.84
     utilising
    0.84
     relying
    0.79
     folos
    0.78
     keeping
    0.76
    using
    0.76
    Activations Density 1.282%

    No Known Activations