© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14280
    Prev
    Next
    INDEX
    Explanations

    phrases related to image manipulation and web design

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    678
    +0.16
    0.5%
    1177
    +0.13
    0.4%
    690
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.09
    1379
    +0.13
    0.07
    100
    +0.13
    0.06
    Negative Logits
    <bos>
    -0.75
    Leggi
    -0.59
    SizeMode
    -0.58
    Caratteristiche
    -0.54
    Життєпис
    -0.54
    Voci
    -0.53
    Versión
    -0.53
    afterEach
    -0.52
    chenta
    -0.51
    WithMany
    -0.51
    POSITIVE LOGITS
     swarovski
    1.30
     unspeak
    1.30
     disagre
    1.29
     hairc
    1.28
     gaily
    1.27
     osal
    1.26
     aen
    1.25
     apprehen
    1.25
     tolerably
    1.24
     thut
    1.21
    Activations Density 0.715%

    No Known Activations