© 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. 2375
    Prev
    Next
    INDEX
    Explanations

    instructions for constructing objects using specific materials

    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
    1385
    +0.18
    0.6%
    906
    +0.14
    0.4%
    876
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.18
    0.05
    2044
    +0.14
    0.05
    1385
    +0.13
    0.04
    Negative Logits
     akut
    -1.22
     praktik
    -1.19
     embra
    -1.18
     kooper
    -1.16
     alkoh
    -1.16
     kollek
    -1.16
     Sén
    -1.15
     endom
    -1.15
     Ibidem
    -1.14
     konserv
    -1.13
    POSITIVE LOGITS
     desired
    0.59
     your
    0.59
     create
    0.58
     slightly
    0.57
     overlap
    0.55
     inside
    0.55
     vertical
    0.53
    <bos>
    0.53
     serce
    0.53
     length
    0.52
    Activations Density 0.260%

    No Known Activations